Best AI papers explained

544 Episodes

1. GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding

   Published: 11/5/2025
2. Beyond a million tokens: benchmarking and enhancing long-term memory in llms

   Published: 11/4/2025
3. Agentic Economic Modeling

   Published: 11/3/2025
4. Emergent Introspective Awareness in Large Language Models

   Published: 11/3/2025
5. Can Large reasoning models self-train?

   Published: 11/1/2025
6. ALITA-G: Self-Evolving Generative Agent for Agent Generation

   Published: 11/1/2025
7. Self-improving LLM agents at test-time

   Published: 10/30/2025
8. Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization

   Published: 10/30/2025
9. Language models are injective and hence invertible

   Published: 10/30/2025
10. ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

    Published: 10/29/2025
11. RLAD: Training LLMs to Discover Abstractions

    Published: 10/29/2025
12. How to Train Your Advisor: Steering Black-Box LLMs with ADVISOR MODELS

    Published: 10/29/2025
13. Self-improving LLM agents at Test-Time

    Published: 10/27/2025
14. KL-Regularized Reinforcement Learning is designed to Mode Collapse

    Published: 10/27/2025
15. How do LLMs use their depth?

    Published: 10/27/2025
16. Thought Communication in Multiagent Collaboration

    Published: 10/27/2025
17. Reasoning with Sampling: Base Models Outperform RL

    Published: 10/26/2025
18. Continual Learning via Sparse Memory Finetuning

    Published: 10/26/2025
19. Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences

    Published: 10/24/2025
20. The Coverage Principle: How Pre-Training Enables Post-Training

    Published: 10/24/2025